297565aa22
Modern compilers are perfectly capable of extracting parallelism from the XOR routines, provided that the prototypes reflect the nature of the input accurately, in particular, the fact that the input vectors are expected not to overlap. This is not documented explicitly, but is implied by the interchangeability of the various C routines, some of which use temporary variables while others don't: this means that these routines only behave identically for non-overlapping inputs. So let's decorate these input vectors with the __restrict modifier, which informs the compiler that there is no overlap. While at it, make the input-only vectors pointer-to-const as well. Tested-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Link: https://github.com/ClangBuiltLinux/linux/issues/563 Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
23 lines
888 B
C
23 lines
888 B
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_POWERPC_XOR_ALTIVEC_H
|
|
#define _ASM_POWERPC_XOR_ALTIVEC_H
|
|
|
|
#ifdef CONFIG_ALTIVEC
|
|
void xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2);
|
|
void xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3);
|
|
void xor_altivec_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4);
|
|
void xor_altivec_5(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4,
|
|
const unsigned long * __restrict p5);
|
|
|
|
#endif
|
|
#endif /* _ASM_POWERPC_XOR_ALTIVEC_H */
|